federating-mcp-servers

federating-mcp-servers is a skill for Claude Code from talayash/spring-fleet. It costs 56 tokens per session (843 once invoked), scanned A, original, MIT.

Instructions for connecting MCP servers—services that provide tools to an AI assistant—from several Spring Boot applications into one shared tool list.

In plain words
What is it for?
Use it when Spring-based services expose their own MCP tools and need to be discovered, configured, authenticated, and connected alongside the main fleet server.
Why use it?
It prevents developers from rebuilding tools that individual services already provide and makes those tools available through one assistant interface.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the spring-fleet plugin — 4 skills, 6 commands, 3 agents, 1 MCP server shipped together

Good fit Use it when Spring-based services expose their own MCP tools and need to be discovered, configured, authenticated, and connected alongside the main fleet server.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add talayash/spring-fleet
Claude Code
/plugin install spring-fleet

Made for: Claude Code.

Or install spring-fleet, the plugin that ships this one along with the rest of its 4 skills, 6 commands, 3 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for federating-mcp-servers

README.md
[![agentmods](https://agentmods.dev/badge/skills/talayash/spring-fleet/federating-mcp-servers.svg)](https://agentmods.dev/skills/talayash/spring-fleet/federating-mcp-servers)
Your own site
<a href="https://agentmods.dev/skills/talayash/spring-fleet/federating-mcp-servers"><img src="https://agentmods.dev/badge/skills/talayash/spring-fleet/federating-mcp-servers.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 843 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00843
Opus 5 $0.00028 $0.00421
Sonnet 5 $0.00011 $0.00169
Haiku 4.5 $0.00006 $0.00084

Measured 8d ago against content hash f91da72d2c3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

federating-mcp-servers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/federating-mcp-servers/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Federating fleet-owned MCP servers

Spring AI 1.1 ships spring-ai-starter-mcp-server-{webmvc,webflux,servlet}, so any Spring Boot service in the fleet can expose @Tool-annotated beans (and selected actuator endpoints) as MCP tools. When that happens, the right move is not to re-implement those tools inside spring-fleet — it is to federate them: register each service's MCP server alongside the spring-fleet MCP server so Claude sees one unified tool surface across the whole fleet.

When to use

/fleet-init records services[].stack.springAiMcpServer = true for any repo whose build declares spring-ai-starter-mcp-server. That flag is your signal.

Procedure

  1. Discover the candidates. Iterate services[] and collect every one with stack.springAiMcpServer == true. For each, you need:

    • the transport URL (Streamable HTTP is the recommended 2026 transport; SSE is being sunset). The default Spring AI MCP server endpoint is http://<host>:<port><contextPath>/mcp. Confirm from each service's application.properties if spring.ai.mcp.server.base-path is set.
    • any required auth header (often a bearer token from the team's IDP).
  2. Register them in the user's MCP client config. Claude Code reads .mcp.json. Append one entry per federated server next to the existing spring-fleet entry, e.g.:

    {
      "mcpServers": {
        "spring-fleet":      { "command": "python", "args": ["${CLAUDE_PLUGIN_ROOT}/scripts/mcp_server.py"] },
        "fleet-inventory":   { "transport": "streamable-http", "url": "http://localhost:8083/inventory-v1/mcp" },
        "fleet-order":       { "transport": "streamable-http", "url": "http://localhost:8081/order-v1/mcp" }
      }
    }
    

    Always prefix the federated server name with fleet- so the namespace is readable and collisions with non-fleet MCP servers are unlikely.

  3. Confirm with the user before editing .mcp.json. Federation changes the agent's effective tool surface and the data it can read — that's a shared-state change worth a quick confirmation. Show the proposed diff.

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 72 lines · 56 tokens per session scan A f91da72d2c3f

Subscribe to this mod's changes

federating-mcp-servers is a skill published in the GitHub repository talayash/spring-fleet (2 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 843 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

logging-standards

Structured logging standards: log levels, structured fields, correlation IDs, PII masking, and event naming. TRIGGER when: adding log statements, configuring loggers, or reviewing log output. SKIP: metrics and alerting (use monitoring-observability); error control flow (use error-handling). (Examples use structlog +…

komluk/scaffolding · 77 tokens

mui-styling

Material-UI (MUI) styling standards: sx-prop priority, theme tokens, spacing scale, responsive design, and accessibility. TRIGGER when: styling MUI components, defining theme tokens, or building responsive layouts. SKIP: component logic and hooks (use react-patterns); cross-stack UX/design decisions (use…

komluk/scaffolding · 76 tokens

sofa-search

Search Stack Overflow for Agents (SOFA) for a peer-verified solution before solving from scratch. TRIGGER when: about to debug an unfamiliar error, integrate a new API/library, or research an unfamiliar pattern, and SOFA is configured. SKIP: trivial/familiar tasks; SOFA unconfigured (no-op); contributing (future…

komluk/scaffolding · 74 tokens

watch-patterns

Correct construction of watchers for long-running operations. TRIGGER when: arming observation of a long-running operation (CI run, deploy, transfer, GC/prune, log stream), writing poll/until loops, or using the Monitor tool. SKIP: defining production alerts/metrics (use monitoring-observability); log formatting (use…

komluk/scaffolding · 76 tokens

agent-memory

3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge. TRIGGER when: reading or writing agent memory files, choosing which memory tier an insight belongs in, or starting a task needing prior context. SKIP: vector recall (use semantic-memory-mcp); distilling conversations into…

komluk/scaffolding · 70 tokens

database-optimization

Schema design, index strategy, migration safety, and query analysis. TRIGGER when: designing tables or indexes, writing a migration, or diagnosing a slow query. SKIP: writing ORM model code (use python-patterns); generic backend patterns (use python-patterns).

komluk/scaffolding · 58 tokens